Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 22247
    Prev
    Next
    INDEX
    Explanations

    superlatives related to quantity or degree

    oai_token-act-pair · gpt-3.5-turbo

    descriptors of effort and capacity related to accomplishments and challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ucky
    -0.66
     quint
    -0.66
     Deadly
    -0.63
    CHAT
    -0.63
     Tactics
    -0.62
    ħĭ
    -0.62
     2025
    -0.60
     Representative
    -0.60
     Hort
    -0.58
     CST
    -0.58
    POSITIVE LOGITS
     nowadays
    0.75
    Ùĩ
    0.71
    uable
    0.69
     âĶľ
    0.68
     hoop
    0.67
     lately
    0.67
    catentry
    0.66
     (>
    0.66
     involved
    0.65
     headaches
    0.65
    Activations Density 0.291%

    No Known Activations